Instructions to use nics-efc/VPR-Qwen3-4B-Sokoban with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nics-efc/VPR-Qwen3-4B-Sokoban with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nics-efc/VPR-Qwen3-4B-Sokoban")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nics-efc/VPR-Qwen3-4B-Sokoban")
model = AutoModelForCausalLM.from_pretrained("nics-efc/VPR-Qwen3-4B-Sokoban", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nics-efc/VPR-Qwen3-4B-Sokoban with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nics-efc/VPR-Qwen3-4B-Sokoban"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nics-efc/VPR-Qwen3-4B-Sokoban",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nics-efc/VPR-Qwen3-4B-Sokoban

SGLang

How to use nics-efc/VPR-Qwen3-4B-Sokoban with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nics-efc/VPR-Qwen3-4B-Sokoban" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nics-efc/VPR-Qwen3-4B-Sokoban",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nics-efc/VPR-Qwen3-4B-Sokoban" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nics-efc/VPR-Qwen3-4B-Sokoban",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nics-efc/VPR-Qwen3-4B-Sokoban with Docker Model Runner:
```
docker model run hf.co/nics-efc/VPR-Qwen3-4B-Sokoban
```

VPR-Qwen3-4B-Sokoban

This is a Qwen3-4B checkpoint trained with Verifiable Process Rewards (VPR) on Markovian Sokoban interactions. At each visited state, VPR samples four action responses, scores their parsed actions with a task-grounded search-based Sokoban oracle, commits one highest-reward candidate, and optimizes all eligible candidates using locally normalized advantages.

Reported result

Evaluation	SR
Sokoban	28.40 ± 2.79

Values are percentages reported under the evaluation protocol in the VPR paper. SR is success rate; CR is completion rate.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "nics-efc/VPR-Qwen3-4B-Sokoban"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

inputs = tokenizer("<current Markovian game prompt>", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Use the environment prompts, parsers, and action conventions in the VPR codebase for reproduction. These task-specific checkpoints are not intended as general-purpose assistants.

Resources

Limitations

Training relies on task-grounded oracle signals and specific Markovian prompts. Performance outside the documented environments and action formats has not been established. Evaluate safety and correctness before open-ended deployment.

Citation

@misc{yuan2026verifiable,
  title         = {Verifiable Process Rewards for Agentic Reasoning},
  author        = {Huining Yuan and Zelai Xu and Huaijie Wang and Xiangmin Yi and Jiaxuan Gao and Xiao-Ping Zhang and Yu Wang and Chao Yu and Yi Wu},
  year          = {2026},
  eprint        = {2605.10325},
  archivePrefix = {arXiv},
  primaryClass  = {cs.AI},
  url           = {https://arxiv.org/abs/2605.10325}
}